Room identification using frequency dependence of spectral decay statistics

File Description SizeFormat 
main_20180214_230204_camera_ready.pdfFile embargoed until 01 January 10000453.31 kBAdobe PDF    Request a copy
Title: Room identification using frequency dependence of spectral decay statistics
Author(s): Moore, AH
Naylor, P
Brookes, DM
Item Type: Conference Paper
Abstract: A method for room identification is proposed based on the reverber- ation properties of multichannel speech recordings. The approach exploits the dependence of spectral decay statistics on the reverber- ation time of a room. The average negative-side variance within 1 / 3 - octave bands is proposed as the identifying feature and shown to be effective in a classification experiment. However, negative-side vari- ance is also dependent on the direct-to-reverberant energy ratio. The resulting sensitivity to different spatial configurations of source and microphones within a room are mitigated using a novel reverberation enhancement algorithm. A classification experiment using speech convolved with measured impulse responses and contaminated with environmental noise demonstrates the effectiveness of the proposed method, achieving 79% correct identification in the most demanding condition compared to 40% using unenhanced signals.
Publication Date: 16-Apr-2018
Date of Acceptance: 14-Feb-2018
ISSN: 0736-7791
Publisher: Institute of Electrical and Electronics Engineers Inc.
Journal / Book Title: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/M026698/1
Conference Name: IEEE Int. Conf. on Acoustics, Speech and Signal Processing
Copyright Statement: This paper is embargoed until publication
Publication Status: Accepted
Start Date: 2018-04-16
Finish Date: 2018-04-20
Conference Place: Calgary, Canada
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering

Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons